Coordinated control system modelling of ultra-supercritical unit based on a new T-S fuzzy structure.

The thermal power plant, especially the ultra-supercritical unit is featured with severe nonlinearity, strong multivariable coupling. In order to deal with these difficulties, it is of great importance to build an accurate and simple model of the coordinated control system (CCS) in the ultra-supercritical unit. In this paper, an improved T-S fuzzy model identification approach is proposed. First of all, the k-means++ algorithm is employed to identify the premise parameters so as to guarantee the number of fuzzy rules. Then, the local linearized models are determined by using the incremental historical data around the cluster centers, which are obtained via the stochastic gradient descent algorithm with momentum and variable learning rate. Finally, with the proposed method, the CCS model of a 1000 MW USC unit in Tai Zhou power plant is developed. The effectiveness of the proposed approach is validated by the given extensive simulation results, and it can be further employed to design the overall advanced controllers for the CCS in an USC unit.

[1]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  Zhang Jianhua,et al.  T-S fuzzy modeling based on compatible relation and its application in power plant , 2011, 2011 6th IEEE Conference on Industrial Electronics and Applications.

[3]  Ataollah Ebrahimzadeh,et al.  Control chart pattern recognition using K-MICA clustering and neural networks. , 2012, ISA transactions.

[4]  Bhim Singh,et al.  DSTATCOM supported induction generator for improving power quality , 2016 .

[5]  Yan-Jun Liu,et al.  Neural network-based adaptive control for a class of chemical reactor systems with non-symmetric dead-zone , 2016, Neurocomputing.

[6]  Igor Skrjanc,et al.  Recursive fuzzy c-means clustering for recursive fuzzy identification of time-varying processes. , 2011, ISA transactions.

[7]  José Antonio Lozano,et al.  An efficient approximation to the K-means clustering for massive data , 2017, Knowl. Based Syst..

[8]  Xi Zhang,et al.  Multi-model Predictive Control of Ultra-supercritical Coal-fired Power Unit , 2014 .

[9]  Tian Haijun,et al.  Modeling of Power Plant Superheated Steam Temperature Based on Least Squares Support Vector Machines , 2012 .

[10]  Mahesh K. Mishra,et al.  Three-leg inverter-based distribution static compensator topology for compensating unbalanced and non-linear loads , 2015 .

[11]  Guolian Hou,et al.  Modeling of a 1000MW power plant ultra super-critical boiler system using fuzzy-neural network methods , 2013 .

[12]  Xiao Wu,et al.  Data-Driven Modeling and Predictive Control for Boiler–Turbine Unit , 2013, IEEE Transactions on Energy Conversion.

[13]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[14]  Xiao Wu,et al.  Fuzzy modeling and predictive control of superheater steam temperature for power plant. , 2015, ISA transactions.

[15]  Dan Wang,et al.  Data stream clustering based on Fuzzy C-Mean algorithm and entropy theory , 2016, Signal Process..

[16]  Ali Sarosh,et al.  A novel KFCM based fault diagnosis method for unknown faults in satellite reaction wheels. , 2012, ISA transactions.

[17]  Fei Liu,et al.  Parameter estimation for a dual-rate system with time delay. , 2014, ISA transactions.

[18]  Yongchao Liu,et al.  Least Square Fast Learning Network for modeling the combustion efficiency of a 300WM coal-fired boiler , 2014, Neural Networks.

[19]  Shaocheng Tong,et al.  Adaptive neural networks output feedback dynamic surface control design for MIMO pure-feedback nonlinear systems with hysteresis , 2016, Neurocomputing.

[20]  C. K. Sundarabalan,et al.  PEM fuel cell supported distribution static compensator for power quality enhancement in three-phase four-wire distribution system , 2014 .

[21]  M. Arefi,et al.  A fast iterative recursive least squares algorithm for Wiener model identification of highly nonlinear systems. , 2017, ISA transactions.

[22]  S. R. Kannan,et al.  Effective fuzzy c-means clustering algorithms for data clustering problems , 2012, Expert Syst. Appl..

[23]  Quan Li,et al.  A New Approach of Modeling an Ultra-Super-Critical Power Plant for Performance Improvement , 2016 .

[24]  Aminollah Khormali,et al.  A novel approach for recognition of control chart patterns: Type-2 fuzzy clustering optimized support vector machine. , 2016, ISA transactions.

[25]  Marcelo Keese Albertini,et al.  Estimating photovoltaic power generation: Performance analysis of artificial neural networks, Support Vector Machine and Kalman filter , 2017 .

[26]  Jizhen Liu,et al.  A dynamic model used for controller design of a coal fired once-through boiler-turbine unit , 2015 .

[27]  Jia Minping,et al.  Segmentation algorithm for small targets based on improved data field and fuzzy c-means clustering , 2015 .

[28]  C. K. Sundarabalan,et al.  Power Quality Enhancement in Power Distribution system using Artificial intelligence based Dynamic Voltage Restorer , 2013 .